Researchers have developed an open-source conversational XAI system called the Explainability Assistant, designed to help facility managers and building operators interpret complex machine learning models used for energy consumption forecasting. This system utilizes the function-calling capabilities of large language models to achieve 94% intent-parsing accuracy, significantly outperforming previous conversational XAI approaches. A comparative evaluation with energy domain specialists showed that the Explainability Assistant offers improved usability and was unanimously preferred over traditional XAI dashboards for practical application. AI
IMPACT Enhances interpretability of complex ML models for energy management, potentially improving operational efficiency.
RANK_REASON The cluster contains an academic paper detailing a new XAI system. [lever_c_demoted from research: ic=1 ai=1.0]
- arXiv
- Energy Consumption Models
- Explainability Assistant
- genetic programming
- large-language models
- TalkToModel
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
